© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 14034
    Prev
    Next
    INDEX
    Explanations

    parking and docking related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    赤
    -0.21
    åĬ³åĬ¡
    -0.20
    æij§
    -0.20
    èĤīä½ĵ
    -0.20
    éĥ¨ä»½
    -0.19
    æĭĦ
    -0.19
     Burgess
    -0.19
     Fat
    -0.19
     Downing
    -0.18
    ware
    -0.18
    POSITIVE LOGITS
    åģľæĶ¾
    0.31
    ä½įç½®
    0.28
    åģľè½¦
    0.28
    åģľè½¦ä½į
    0.25
    车ä½į
    0.25
     parking
    0.23
    åģľè½¦åľº
    0.22
    姿åĬ¿
    0.22
    妥
    0.21
     parked
    0.21
    Activations Density 0.024%

    No Known Activations